中文
相关论文

相关论文: Quantification of Deep Neural Network Prediction U…

200 篇论文

Deep neural networks (DNNs) have achieved tremendous success in computer vision, natural language processing, and scientific and engineering domains. However, DNNs can make unexpected, incorrect, yet overconfident predictions, leading to…

机器学习 · 计算机科学 2025-12-16 Wenchong He , Zhe Jiang , Tingsong Xiao , Zelin Xu , Yukun Li

Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning,…

系统与控制 · 电气工程与系统科学 2025-03-25 Xu Wu , Lesego E. Moloko , Pavel M. Bokov , Gregory K. Delipei , Joshua Kaizer , Kostadin N. Ivanov

Uncertainty quantification (UQ) is an important component of molecular property prediction, particularly for drug discovery applications where model predictions direct experimental design and where unanticipated imprecision wastes valuable…

机器学习 · 计算机科学 2020-05-21 Lior Hirschfeld , Kyle Swanson , Kevin Yang , Regina Barzilay , Connor W. Coley

Reliable uncertainty quantification on RUL prediction is crucial for informative decision-making in predictive maintenance. In this context, we assess some of the latest developments in the field of uncertainty quantification for…

机器学习 · 计算机科学 2023-02-10 Luis Basora , Arthur Viens , Manuel Arias Chao , Xavier Olive

Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with…

机器学习 · 计算机科学 2023-02-08 Apostolos F Psaros , Xuhui Meng , Zongren Zou , Ling Guo , George Em Karniadakis

We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural…

高能物理 - 实验 · 物理学 2023-11-02 Dae Heun Koh , Aashwin Mishra , Kazuhiro Terao

We present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods - Bayesian Neural Networks (BNN),…

机器学习 · 计算机科学 2020-12-08 João Caldeira , Brian Nord

Traditional deep learning (DL) models are powerful classifiers, but many approaches do not provide uncertainties for their estimates. Uncertainty quantification (UQ) methods for DL models have received increased attention in the literature…

机器学习 · 计算机科学 2023-08-14 Daniel Ries , Joshua Michalenko , Tyler Ganter , Rashad Imad-Fayez Baiyasi , Jason Adams

Neural Network (NN) models provide potential to speed up the drug discovery process and reduce its failure rates. The success of NN models require uncertainty quantification (UQ) as drug discovery explores chemical space beyond the training…

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This…

机器学习 · 计算机科学 2024-07-02 Shengli Jiang , Shiyi Qin , Reid C. Van Lehn , Prasanna Balaprakash , Victor M. Zavala

Machine learning (ML) offers promising new approaches to tackle complex problems and has been increasingly adopted in chemical and materials sciences. Broadly speaking, ML models employ generic mathematical functions and attempt to learn…

材料科学 · 物理学 2024-08-21 Jin Dai , Santosh Adhikari , Mingjian Wen

Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory, however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked.…

核理论 · 物理学 2025-10-29 Mengyao Huang , Kyle A. Wendt , Nicolas F. Schunck , Erika M. Holmbeck

Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify the uncertainty of their…

机器学习 · 计算机科学 2025-11-14 Adrien Lafage , Olivier Laurent , Firas Gabetni , Gianni Franchi

With increasing computational demand, Neural-Network (NN) based models are being developed as pre-trained surrogates for different thermohydraulics phenomena. An area where this approach has shown promise is in developing higher-fidelity…

流体动力学 · 物理学 2024-12-13 Cody Grogan , Som Dutta , Mauricio Tano , Somayajulu L. N. Dhulipala , Izabela Gutowska

On top of machine learning models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and…

机器学习 · 计算机科学 2024-03-28 Venkat Nemani , Luca Biggio , Xun Huan , Zhen Hu , Olga Fink , Anh Tran , Yan Wang , Xiaoge Zhang , Chao Hu

Deep learning has been shown to be highly effective for automatic modulation classification (AMC), which is a pivotal technology for next-generation cognitive communications. Yet, existing deep learning methods for AMC often lack robust…

信号处理 · 电气工程与系统科学 2025-12-03 Huian Yang , Rajeev Sahay

Uncertainty quantification (UQ) helps to make trustworthy predictions based on collected observations and uncertain domain knowledge. With increased usage of deep learning in various applications, the need for efficient UQ methods that can…

机器学习 · 计算机科学 2021-11-09 Olga Graf , Pablo Flores , Pavlos Protopapas , Karim Pichara

Uncertainty quantification (UQ) in machine learning is currently drawing increasing research interest, driven by the rapid deployment of deep neural networks across different fields, such as computer vision, natural language processing, and…

机器学习 · 计算机科学 2022-08-26 Zongren Zou , Xuhui Meng , Apostolos F Psaros , George Em Karniadakis

Uncertainty quantification (UQ) is important for reliability assessment and enhancement of machine learning models. In deep learning, uncertainties arise not only from data, but also from the training procedure that often injects…

机器学习 · 统计学 2023-11-13 Ziyi Huang , Henry Lam , Haofeng Zhang

The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive…

机器学习 · 计算机科学 2024-01-02 Deepak Akhare , Tengfei Luo , Jian-Xun Wang
‹ 上一页 1 2 3 10 下一页 ›